Identifying and measuring potential sources of pollution is essential for water management and pollution control. Using a range of artificial intelligence models to analyze water quality (WQ) is one of the most effective techniques for estimating water quality index (WQI). In this context, machine learning–based models are introduced to predict the WQ factors of Southeastern Black Sea Basin. The data comprising monthly samples of different WQ factors were collected for 12 months at eight locations of the Türkiye region in Southeastern Black Sea. The traditional evaluation with WQI of surface water was calculated as average (i.e. good WQ). Single multiplicative neuron (SMN) model, multilayer perceptron (MLP) and pi-sigma artificial neural networks (PS-ANNs) were used to predict WQI, and the accuracy of the proposed algorithms were compared. SMN model and PS-ANNs were used for WQ prediction modeling for the first time in the literature. According to the results obtained from the proposed ANN models, it was found to provide a highly reliable modeling approach that allows capturing the nonlinear structure of complex time series and thus to generate more accurate predictions. The results of the analyses demonstrate the applicability of the proposed pi-sigma model instead of using other computational methods to predict WQ both in particular and other surface water resources in general.

In this study is to determine the current heavy metal and antibiotic resistance levels of isolates taken from the Gelevera Creek (Giresun). For this purpose, surface water and sediment were collected monthly from four different stations starting from April 2017 and ending in March 2018. After the Gr (-) and Gr (+) bacteria isolation in selective media, the 325 isolated were tested for their resistance against 4 different heavy metals. The resistance levels of these 325 bacteria against to cadmium, copper, lead and manganese heavy metals were detected respectively as 89.0%, 60.16%, 33.0%, 29.8% (Cd > Cu > Pb > Mn). The 82 isolates with high resistance against heavy metals in each station were also tested for their resistance against antibiotics. The levels of resistance against antibiotics of these isolated strains were found respectively as follows: cefazolin: 69.6%, cefuroxime: 59.4%, nalidixic acid: 51.7%, ampicillin: 46.0%, cefotaxime: 39.1%, meropenem: 31.4%, amikacin: 21.7%, erythromycin: 13.0%, and chloramphenicol: 3.3%. In our study, two isolates with high antibiotic and heavy metal, using the Vitek-II Compact System were identified as Serratia marcenscens (99%) and Enterococcus avium (91%). Furthermore, the multiple antibiotic resistance levels (MAR) of all isolates are 80,5%. The results indicate that the isolates taken from the Gelevera Creek (Giresun) were found to be extremely resistant against commercially used antibiotics and heavy metals, and this shows that there is antibiotic and heavy metal contamination in drinking water reserves.

This study presents a comprehensive bibliometric analysis of global research on condition factor (K) and length–weight relationships (LWR) in fisheries science between 2000 and mid-2025. Utilizing data extracted from the Web of Science (WoS) Core Collection, a total of 760 peer-reviewed articles were analyzed through the RStudio Bibliometrix (2025.05.0) and its Biblioshiny interface. The analysis examined publication trends, authorship patterns, international collaborations, citation metrics, and keyword dynamics. Network and thematic mapping techniques, including co-citation and keyword co-occurrence analyses, were employed to uncover the intellectual structure and thematic evolution of the field. The findings reveal a growing academic interest and thematic diversification over the past two and a half decades, particularly after 2010. The research focus has expanded from foundational biological assessments to applied areas such as aquaculture, environmental monitoring, and ecotoxicology. Although international collaboration remains moderate, significant contributions from countries such as China, Bangladesh, and the United States underscore a globally distributed research landscape. The study emphasizes the need for broader regional representation and interdisciplinary integration to support sustainable fisheries management and aquatic ecosystem health.

Amaç: Bu çalışma, yapay zekâ teknolojilerinin evde bakım hizmetlerindeki rolünü ve bu alandaki akademik literatürün gelişimini bibliyometrik bir analiz yöntemiyle incelenmesi amacıyla yapılmıştır. Yöntem: Araştırmanın verileri, 1 Nisan 2025 tarihinde Web of Science (WoS) veri tabanından Ocak 2014 – Mart 2025 yılları arasındaki yayınlar arasından seçilmiştir. Bibliyometrik analiz kapsamında, "home care" ve "artificial intelligence" anahtar sözcükleriyle yapılan aramalar sonucunda 735 yayın tespit edilmiştir. Bu yayınlar, VOSviewer yazılımı aracılığıyla performans analizi ve bilimsel haritalama teknikleri kullanılarak değerlendirilmiştir. Bulgular: Araştırma sonuçları, özellikle COVID-19 sonrası dönemde YZ tabanlı çözümlere odaklanmada büyük bir artış olduğunu göstermektedir. Bu eğilim, yayın sayısında ve işbirlikçi yapıların büyümesinde görülmektedir.Sonuç olarak, YZ’nın ve ML'nin evde bakım hizmetlerinde entegrasyonu; anahtar kelime çalışmalarına göre “yapay zeka”, “makine öğrenimi” ve “teletıp” gibi kavramlar yalnızca çalışma konusu olmakla kalmayıp, aynı zamanda evde bakım hizmetlerinin dijital dönüşümünde de temel unsurlardır. Sonuç: Bu çalışma, yapay zekânın evde bakım hizmetlerindeki dönüştürücü potansiyelini ve bu alandaki araştırmaların gelecekteki yönelimlerini anlamaya yönelik önemli bir katkı sunmaktadır. Gelecekteki araştırmaların farklı veritabanlarını birleştirerek ve meta-analiz gibi yöntemleri entegre ederek literatürü daha kapsamlı bir şekilde ele alması önerilir.

Artificial intelligence-based methods have gained increasing attention for sustainable environmental monitoring due to their efficiency and low operational cost. In this study, a new long short-term memory with an exponential smoothing method is proposed, and an arithmetic mean optimization algorithm-based training strategy is introduced for the proposed neural networks. The resulting proposed neural network method is used to forecast chlorophyll-a concentrations, a key indicator of algal bloom dynamics, using satellite-derived time series data from 15 estuarine monitoring stations in the Black Sea region. To evaluate the effectiveness of this framework, comprehensive experiments are conducted by comparing the proposed neural network with several shallow and deep learning models. The results show that the proposed neural network model achieves superior forecasting performance in terms of root mean square error and mean absolute percentage error across the majority of the analysed time series. Furthermore, statistical significance analyses based on the Friedman and Wilcoxon signed-rank tests confirm that the observed performance improvements are statistically significant. The proposed neural network model attains the best overall ranking with a mean rank of 1.06 and significantly outperforms all competing models under the Holm-Bonferroni correction. The findings indicate that the proposed neural network improves both forecasting accuracy and robustness, providing a reliable and effective framework for modelling chlorophyll-a dynamics. This approach offers a promising tool for the early detection and management of algal bloom events in marine ecosystems.